Wayne Wu

wayne_wu.jpg

I am an AI Researcher in the Department of Computer Science at the University of California, Los Angeles (UCLA), working with Bolei Zhou, and collaborating with Trevor Darrell (UC Berkeley EECS) and Jiaqi Ma (UCLA CEE). I was a Visiting PhD at MMLab, Nanyang Technological University, working with Chen Change Loy. I received my Ph.D. from the Department of Computer Science and Technology at Tsinghua University, with a two-year leave for a startup.

My research has been recognized by the UCLA Chancellor’s Award, a CVPR Best Paper Candidate recognition, and multiple Oral/Highlight/Spotlight presentations at top-tier conferences, including CVPR, ICLR, and NeurIPS. I also bring over seven years of experience in a leading AI startup, where I led a 40+ person R&D team to deliver large-scale AI products serving 10M+ end users. My work has been widely featured by media outlets such as VentureBeat, Vice, MarkTechPost, and Weights & Biases. My work has further generated broader community impact through open-source projects with 12K+ GitHub stars and datasets with 100K+ downloads.

"I build world simulators and models for physical AI; I put people first, always."

Research

My research lies at the intersection of computer vision, robotics, and computer graphics. I aim to develop general physical AI systems that are scalable, agentic, and safe in the open world. In the long term, I envision intelligent mobility and service systems that assist people in everyday urban life and make cities more efficient, sustainable, and accessible.

To realize this vision, I focus on three fundamental challenges: scaling the world models and environments in which agents learn, enabling agents to learn and adapt through embodied experience, and ensuring safe interaction with people.

  • Scalable World Models & Simulators: Building large-scale, interactive robot-learning platforms from real-world videos and diverse digital assets, with open-ended urban environments for efficient training and evaluation, as in UrbanVerse, URBAN-SIM, MetaUrban, Vid2Sim, and OmniObject3D.
  • Agentic Physical Intelligence: Building adaptive embodied agents that perceive and reason about both their internal states and external environments, plan and act through physical skills, and self-improve through interaction and experience, as in Visually Grounded Humanoid Agents and EmbodiedHuman.
  • Human-Centered Safety: Modeling people across appearance, motion, and interactive behavior, from high-fidelity 4D humans to reactive pedestrians; and developing human-aware robots that operate safely and reliably in populated environments, as in DNA-Rendering, SynBody, PedGen, and SidewalkBench.

Recent Talks and Lectures

From Scaling up to Scaling out: Reality World Simulators for Physical AI

[May 2026] · UMich EECS 542: Advanced Topics in Computer Vision
Slides

Jun, 2026 Invited talk @ ScaleBot Workshop @ CVPR 2026.
Jun, 2026 Invited talk @ Embodied AI Workshop @ CVPR 2026.
Jun, 2026 Invited talk @ Area Chair Workshop @ CVPR 2026.
May, 2026 Invited talk @ Meta Superintelligence Labs.
Apr, 2026 Invited talk @ Purdue University.
Apr, 2026 Guest lecture @ University of Michigan, Ann Arbor.
Apr, 2026 Invited talk @ University of Michigan, Ann Arbor.
Mar, 2026 Invited talk @ Stony Brook University.
Mar, 2026 Invited talk @ Rutgers University.
Feb, 2026 Invited talk @ The University of Texas at Dallas.
Dec, 2025 Invited talk, “Scaling Physical AI via Reality World Simulators”, @ Purdue, hosted by Maggie Zhu and David I. Inouye.
Nov, 2025 Invited talk, “Scaling Physical AI via Reality World Simulators”, @ UIUC, hosted by Shenlong Wang.
Nov, 2025 Invited talk, “Scaling Physical AI via Reality World Simulators”, @ NYU, hosted by Chen Feng.
Nov, 2025 Invited talk, “Scaling Physical AI via Reality World Simulators”, @ Princeton, hosted by Jia Deng.
Nov, 2025 Guest lecture, “Scaling Physical AI via Reality World Simulators”, @ LSU, hosted by Dong Lao.
Nov, 2025 Invited talk, “Scaling Physical AI via Reality World Simulators”, @ JHU, hosted by Tianmin Shu and Alan Yuille.
Oct, 2025 Tutorial, “Scaling Physical AI via Structured World Simulators”, @ DriveX Tutorial @ ICCV 2025.
Oct, 2025 Guest lecture, “Building Scalable, Human-Centric Physical AI Systems”, @ Upenn, hosted by Lingjie Liu.
Jul, 2025 Invited talk, “Building Scalable Physical AI Systems”, @ SVL Lab in Stanford, hosted by Jiajun Wu.
Jul, 2025 Invited talk, “Building Scalable Physical AI Systems”, @ Roblox, hosted by David Durst.
Jun, 2025 Invited talk, “Scaling-up Urban Simulation for Autonomous Micro-mobility”, @ Real-to-Sim Workshop @ CVPR 2025.
Feb, 2025 Invited talk, “Scaling-up Urban Simulation for Autonomous Micro-mobility”, @ BAIR Lab in UC Berkeley, hosted by Trevor Darrell and Angjoo Kanazawa.
Jun, 2024 Invited talk, “Simulation Platforms for Embodied AI in Urban Spaces”, @ POETS Workshop @ CVPR 2024.
Apr, 2024 Guest lecture, “Autonomous Agents and Foundation Models”, @ UCLA, hosted by Bolei Zhou.

News

Aug, 2026 I will serve as Area Chair at ICLR 2027.
Jun, 2026 I am honored as an Outstanding Area Chair at CVPR 2026. 🏆
Oct, 2025 I am honored with the UCLA Chancellor’s Award 2025, as the only awardee in School of Engineering. 🏆
May, 2025 We are organizing the workshop on Real-to-Sim: Bridging the Gap between Neural Rendering and Robot Learning at CVPR 2025. 🔥
May, 2025 We are organizing the workshop on Embodied “Humans”: Symbiotic Intelligence Between Virtual Humans and Humanoid Robots at CVPR 2025. 🔥
Jan, 2025 We released MetaUrban – a simulation platform for Embodied AI in urban spaces. Try it now!
Mar, 2024 We are organizing the workshop on Virtual Humans for Robotics and Autonomous Driving at CVPR 2024.
Jun, 2023 OmniObject3D is selected as Best Paper Candidate at CVPR 2023. 🏆
Oct, 2022 I am leading OpenXDLab – a new large-scale open-source data platform!
Aug, 2020 We are organizing Workshop on Sensing, Understanding and Synthesizing Humans, ECCV 2020.
Jul, 2020 We released MMAction2 – OpenMMLab’s Next Generation Action Understanding Toolbox.
Jul, 2020 We released MMEditing – OpenMMLab’s Image and Video Editing Toolbox.
Oct, 2019 We are organizing Workshop on Statistical Deep Learning for Computer Vision, ICCV 2019.

Selected Publications

  1. Cue the Flow: Steering Flow-Matching Policies for Open-World Delivery Manipulation
    Haoxuan Wang, Griffin Galimi, Junhua Huang, Selina Song,  Wayne Wu, Yan Yan, and Bolei Zhou
    Technical report, 2026
  2. Looking Back to Move Forward: Temporal Verification for Generative Robot Policies
    Haoxuan Wang,  Wayne Wu, Yan Yan, and Bolei Zhou
    Technical report, 2026
  3. Where to Start: Bridging Embodied Search and Manipulation with Executor-Aware Pose Selection
    Quanzhou Li, Zhonghua Wu,  Wayne Wu, Chen Change Loy, and Bo Dai
    Technical report, 2026
  4. Visually-grounded Humanoid Agents
    Hang Ye, Xiaoxuan Ma, Fan Lu,  Wayne Wu, Kwan-Yee Lin, and Yizhou Wang
    Technical report, arXiv:2604.08509, 2026
    arXiv Project Page
  5. UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos
    Mingxuan Liu*, Honglin He*, Elisa Ricci,  Wayne Wu, and Bolei Zhou
    International Conference on Learning Representations (ICLR), 2026
    arXiv Project Page
  6. From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
    Honglin He, Yukai Ma,  Wayne Wu, and Bolei Zhou
    International Conference on Learning Representations (ICLR), 2026
    arXiv Project Page
  7. Learning Sidewalk Autopilot from Multi-Scale Imitation with Corrective Behavior Expansion
    Honglin He, Yukai Ma, Brad Squicciarini,  Wayne Wu, and Bolei Zhou
    International Conference on Robotics and Automation (ICRA), 2026
  8. Towards Autonomous Micromobility through Scalable Urban Simulation
    Wayne Wu *, Honglin He*, Chaoyuan Zhang, Jack He, Seth Z. Zhao, Ran Gong, Quanyi Li, and Bolei Zhou
    Computer Vision and Pattern Recognition (CVPR), 2025
    arXiv Project Page
    HighlightSelected: 388 / 13,008 (3.0%)
  9. Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
    Ziyang Xie, Zhizheng Liu, Zhenghao Peng,  Wayne Wu, and Bolei Zhou
    Computer Vision and Pattern Recognition (CVPR), 2025
    arXiv Project Page
  10. MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility
    Wayne Wu *, Honglin He*, Jack He, Yiran Wang, Chenda Duan, Zhizheng Liu, Quanyi Li, and Bolei Zhou
    International Conference on Learning Representations (ICLR), 2025
    arXiv YouTube Project Page
    SpotlightSelected: 85 / 11,603 (0.7%)
  11. CosmicMan: A Text-to-Image Foundation Model for Humans
    Shikai Li, Jianglin Fu, Kaiyuan Liu, Wentao Wang, Kwan-Yee Lin, and Wayne Wu †
    Computer Vision and Pattern Recognition (CVPR), 2024
    arXiv YouTube Project Page
    HighlightSelected: 324 / 11,532 (2.8%)
  12. DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering
    Contributors to DNA-Rendering
    International Conference on Computer Vision (ICCV), 2023
    arXiv YouTube Project Page
    Dataset 5K+ Downloads
  13. SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling
    Zhitao Yang, Zhongang Cai, Haiyi Mei, Shuai Liu, Zhaoxi Chen, Weiye Xiao, Yukun Wei, Zhongfei Qing, Chen Wei, Bo Dai,  Wayne Wu, Chen Qian, Dahua Lin, Ziwei Liu, and Lei Yang
    International Conference on Computer Vision (ICCV), 2023
    arXiv YouTube Project Page
  14. OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
    Tong Wu, Jiarui Zhang, Xiao Fu, Yuxin Wang, Jiawei Ren, Liang Pan,  Wayne Wu, Lei Yang, Jiaqi Wang, Chen Qian, Dahua Lin, and Ziwei Liu
    Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    arXiv Project Page
    Best Paper CandidateSelected: 12 / 9,155 (0.1%)